Partial Least Squares Discriminant Analysis Research Articles

Infrared spectroscopy as a new approach for early fabry disease screening: a pilot study

BackgroundFabry disease (FD) is a rare X-linked lysosomal storage disorder marked by alpha-galactosidase-A (α-Gal A) deficiency, caused by pathogenic mutations in the GLA gene, resulting in the accumulation of glycosphingolipids within lysosomes. The current screening test relies on measuring α-Gal A activity. However, this approach is limited to males. Infrared (IR) spectroscopy is a technique that can generate fingerprint spectra of a biofluid’s molecular composition and has been successfully applied to screen numerous diseases. Herein, we investigate the discriminating vibration profile of plasma chemical bonds in patients with FD using attenuated total reflection Fourier-transform IR (ATR-FTIR) spectroscopy.ResultsThe Fabry disease group (n = 47) and the healthy control group (n = 52) recruited were age-matched (39.2 ± 16.9 and 36.7 ± 10.9 years, respectively), and females were predominant in both groups (59.6% and 65.4%, respectively). All patients had the classic phenotype (100%), and no late-onset phenotype was detected. A generated partial least squares discriminant analysis (PLS-DA) classification model, independent of gender, allowed differentiation of samples from FD vs. control groups, reaching 100% sensitivity, specificity and accuracy.ConclusionATR-FTIR spectroscopy harnessed to pattern recognition algorithms can distinguish between FD patients and healthy control participants, offering the potential of a fast and inexpensive screening test.

Identification of Cervi cornu pantotrichum and its mixed varieties by UHPLC-QTOF-MS and UHPLC-TQS-MS/MS

Sika deer (Cervus nippon Temminck) and red deer (Cervus elaphus Linnaeus) are the two creatural sources of velvet antlers, which are recorded in the Chinese Pharmacopoeia (2020 edition). However, the counterfeits-moose (Alces alces Linnaeus) antlers are selling as genuine products in the market. In order to strengthen antler quality control and market supervision, a UHPLC-QTOF-MS coupled with chemometrics analysis and UHPLC-TQS-MS were developed and applied to distinguish the Velvet Antler of moose from that of sika deer and red deer. Firstly, the QTOF-MS quantized data obtained from samples treated with trypsin were subjected to principal component analysis (PCA) to classify these three kinds of antlers. Then, the potential differential marker peptides were found with orthogonal partial least-squares discriminant analysis (OPLS-DA). Finally, validation of these differential marker peptides was assessed using UHPLC-QTOF-MS, and the results showed that the specific ion pairs (m/z 724.8 → 518.1, m/z 724.8 → 938.3, m/z 732.8 → 526.3, m/z 732.8 → 784.3) were detected in moose deer antler, not in velvet antler of sika deer (Cervus nippon Temminck) and red deer (Cervus elaphus Linnaeus). The methods in the paper and specific ion pairs could be successfully applied to distinguish moose antlers from sika deer antlers and red deer antlers.

Comparative Metabolite Profiling of Three Savannic Species of Banisteriopsis (Malpighiaceae) via UPLC-MS/MS and Chemometric Tools.

Banisteriopsis (Malpighiaceae) is an important genus of neotropical savannas with related biological and medicinal activities but under-explored metabolomic profiles. We present a chemometric analysis for discriminating secondary metabolites of three species of Banisteriopsis (B. laevifolia, B. malifolia, and B. stellaris) leaves. Initially, each species was separately extracted with ethanol:water (4 : 1, v/v) and analysed by Ultra Performance Liquid Chromatography coupled with Mass Spectrometry (UPLC-MS/MS). The chromatographic profiles were subjected to Global Natural Product Social (GNPS) and Partial Least Squares Discriminant Analysis (PLS-DA). Eighty-nine compounds (cosine≥0.90) were annotated, including flavonoids, phenolics, and acids. The chemometric analysis (VIP Score) showed each species' relative concentration of the more relevant compounds. In addition, four compounds that discriminate the metabolomic profiles of B. laevifolia, B. malifolia, and B. stellaris were identified by PLS-DA.

Detection of serum alterations in polysubstance use patients by FT-Raman spectroscopy

Substance use disorders pose significant health risks and treatment challenges due to the diverse interactions between substances and their impact on physical and mental health. The chemical effects of multiple substance use on bodily fluids are not yet fully understood. Therefore, this study aimed to investigate the chemical changes induced by a combination of substances compared to a control group. Analysis of FT-Raman spectra revealed structural alterations in the amide III, I, and C = O functional groups of lipids in subjects treated with opioids, alcohol and cannabis (polysubstance group). These changes were evident in the form of peak shifts compared to the control group. Additionally, an imbalance in the amide-lipid ratio was observed, indicating perturbations in serum protein and lipid levels. Furthermore, a 2D plot of two-track two-dimensional correlation spectra (2T2D-COS) demonstrated a shift towards dominance of lipid vibrations in the polysubstance use groups, contrasting with the predominance of the amide fraction in the control group. This observation suggests distinct molecular changes induced by multiple substance use, potentially contributing to the pathophysiology of substance use disorders. Principal Component Analysis (PCA) was utilized to visualize the data structure and identify outliers. Subsequently, Partial Least Squares Discriminant Analysis (PLS-DA) was employed to classify the polysubstance use and control groups. The PLS-DA model demonstrated high classification accuracy, achieving 100.00 % in the training dataset and 94.74 % in the test dataset. Furthermore, receiver operating characteristic (ROC) analysis yielded perfect AUC values of 1.00 for both the training and test sets, underscoring the robustness of the classification model.This study highlights the quantitative and qualitative changes in serum protein and lipid levels induced by polysubstance use groups, as evidenced by FT-Raman spectroscopy. The findings underscore the importance of understanding the chemical effects of polysubstance use on bodily fluids for improved diagnosis and treatment of substance use disorders. Moreover, the successful classification of spectral data using machine learning techniques emphasizes the potential of these approaches in clinical applications for substance abuse monitoring and management.

Metabolomic profiling reveals the step-wise alteration of bile acid metabolism in patients with diabetic kidney disease

BackgroundDiabetic kidney disease (DKD) is the major complication of diabetes concomitant with gut dysbiosis and glycometabolic disorder, which are strongly associated with bile acid (BA) metabolism. Yet studies investigating the BA metabolism involving in DKD pathogenesis are limited. This study aimed to explore the metabolomic profiling of BAs in DKD and analyze its association with DKD progression.MethodsAn ultra-performance liquid chromatography tandem mass spectrometry (UPLC-MS/MS) method was established to quantify BAs in the plasma, fecal and urine samples of patients with DKD or T2DM and healthy individuals (n = 30 for each group). The key BAs associated with DKD were identified by orthogonal partial least-squares discriminant analysis (OPLS-DA) and receiver-operating characteristic (ROC) curve. Polynomial regression and Pearson’s correlation analyses were performed to assess the correlation between the key BAs and the clinical indicators reflecting DKD progression.ResultsMetabolomic profiling of 50 kinds of BAs presented the markedly step-wise alterations of BAs in plasma and feces as well as the little in urine of patients with DKD. Eight kinds of BAs in the plasma, eight kinds in the feces and three kinds in the urine were abnormally expressed, accompanying with the increased conjugated/unconjugated ratios of cholic acid, deoxycholic acid, chenodeoxycholic acid, ursodeoxycholic acid and hyocholic acid in the plasma, and of cholic acid, chenodeoxycholic acid and lithocholic acid in the feces. Moreover, the increased plasma level of glycochenodeoxycholic acid, and the increased fecal levels of glycolithocholic acid, 7-ketodeoxycholic acid and chenodeoxycholic acid-3-β-D-glucuronide are strongly correlated with the clinical indicators reflecting DKD progression, including eGFR, 24 h urinary protein and 24 h urinary microalbumin.ConclusionsOur study for the first time disclosed the specific alterations of BA metabolism reflecting the step-wise progression of DKD, providing the basis for early identification and therapeutical strategies for DKD.

The vaginal metabolomics profile with features of polycystic ovary syndrome: a pilot investigation in China.

Polycystic ovary syndrome (PCOS) is the most common metabolic disorder and reproductive endocrine disease, posing an elevated risk to women of reproductive age. Although metabolism differences in serum, amniotic fluid and urine have been documented in PCOS, there remains a paucity of evidence for vaginal fluid. This study aimed to identify the metabolic characteristics and potential biomarkers of PCOS in Chinese women of reproductive age. We involved ten newly diagnosed PCOS women who attended gynecology at Zhongda Hospital and matched them with ten healthy controls who conducted health check-up programs at Gulou Maternal and Child Health Center in Nanjing, China from January 1st, 2019 to July 31st, 2020. Non-targeted metabolomics based on ultra-high-performance liquid chromatography tandem mass spectrometry (UHPLC-MS/MS) was applied to differentially screen vaginal metabolites between PCOS group and healthy controls. Principal component analysis (PCA), orthogonal partial least-squares discriminant analysis (OPLS-DA) and enrichment analysis were used to observe differences, search for potential biomarkers and enrich related pathways. Among the 20 participants, a total of 195 different metabolites were detected between PCOS group and healthy control group. PCOS and control groups were effectively separated by vaginal fluid. Lipids and lipid-like molecules constituted the majority of differential metabolites. Notably, dopamine exhibited an increased trend in PCOS group and emerged as the most significant differential metabolite, suggesting its potential as a biomarker for identifying PCOS. The application of UHPLC-MS/MS based vaginal metabolomics methods showed significant differences between PCOS and non-PCOS healthy control groups, especially linoleic acid metabolism disorder. Most differential metabolites were enriched in pathways associated with linoleic acid metabolism, phenylalanine metabolism, tyrosine metabolism, nicotinate and nicotinamide metabolism or arachidonic acid metabolism. In this pilot investigation, significant metabolomics differences could be obtained between PCOS and healthy control groups. For PCOS women of reproductive age, vaginal metabolism is a more economical, convenient and harmless alternative to provide careful personalized health diagnosis and potential targets for therapeutic intervention.

Classification of Kudoa thyrsites infected and uninfected fish using a handheld near-infrared spectrophotometer, SIMCA and PLS-DA.

Kudoa thyrsites infection of marine fish typically results in myoliquefaction, which is only apparent 24 to 56 h post-mortem. The traditional methods for the detection of K. thyrsites infected fish are time-consuming and destructive, reducing its marketability. This poses a challenge for the fish industry to remove infected fish before it reaches the market or further processing activities. This study investigated the use of near-infrared (NIR) spectroscopy, in combination with soft independent modelling of class analogy (SIMCA) and partial least square discriminant analysis (PLS-DA), for discriminating K. thyrsites infected fish from uninfected fish. Performance of the classification models was evaluated by calculating the sensitivity, specificity and precision. A total of 334 fish samples (200 sardine, 64 hake and 70 kingklip) were used for this study. Infection of K. thyrsites was determined with the use of qPCR assays. Ninety per cent (90%) of the sardine samples, 78% of the hake samples and 37% of the kingklip samples were infected. Class groups of infected and uninfected fish samples were created for the purpose of generating SIMCA and PLS-DA classification models for each species of fish, as well as for a species independent data set. Principal component analysis (PCA) of NIR spectra did not show any clustering for infected and uninfected samples. Calibration and test sample sets were generated for the purpose of building and testing the SIMCA and PLD-DA classification models. SIMCA and PLS-DA were unable to classify test samples correctly into the two classes. The number of misclassifications (NMC) was higher for the SIMCA models than for the PLS-DA models, with more than 60% incorrectly classified. SIMCA classified most of the test samples into both classes. The precision for PLS-DA were 89% for sardine, 81% for hake, 0% for kingklip and 87% for species independent models, however, most samples were classified at infected. The use of NIR spectroscopy and classification models such as SIMCA and PLS-DA showed limited use as a method to distinguish between K. thyrsites infected and uninfected fish samples. Textural and chemical changes during extended frozen storage of the fish samples may have masked the effects associated with K. thyrsites infection. Further studies are suggested where NIR spectroscopy is used in combination with texture analysis and image spectroscopy.

Near-infrared spectroscopy combined with support vector machine for the identification of Tartary buckwheat (Fagopyrum tataricum (L.) Gaertn) adulteration using wavelength selection algorithms

The frequent occurrence of adulterating Tartary buckwheat powder with crop flours in the market necessitates an urgent need for a simple analysis method to ensure the quality of Tartary buckwheat. This study employed near-infrared spectroscopy (NIRS) for the collection of spectral data from Tartary buckwheat samples adulterated with whole wheat, oat, soybean, barley, and sorghum flours. The competitive adaptive reweighted sampling (CARS) and successive projection algorithm (SPA) were deployed to identify informative wavelengths. By integrating support vector machine (SVM) and partial least squares discriminant analysis (PLS-DA), we constructed qualitative models to discern Tartary buckwheat adulteration. The PLS-DA model exhibited prediction accuracies between 89.78 % and 94.22 %, while the mean-centering (MC)-PLS-DA model showcased impressive predictive accuracy of 93.33 %. Notably, the feature-based Autoscales-CARS-CV-SVM model achieved more excellent identification accuracy. These findings exhibit the excellent potential of chemometrics as a powerful tool for detecting food product adulteration.

Identifying Process Differences with ToF-SIMS: An MVA Decomposition Strategy.

In time-of-flight secondary ion mass spectrometry (ToF-SIMS), multivariate analysis (MVA) methods such as principal component analysis (PCA) are routinely employed to differentiate spectra. However, additional insights can often be gained by comparing processes, where each process is characterized by its own start and end spectra, such as when identical samples undergo slightly different treatments or when slightly different samples receive the same treatment. This study proposes a strategy to compare such processes by decomposing the loading vectors associated with them, which highlights differences in the relative behavior of the peaks. This strategy identifies key information beyond what is captured by the loading vectors or the end spectra alone. While PCA is widely used, partial least-squares discriminant analysis (PLS-DA) serves as a supervised alternative and is the preferred method for deriving process-related loading vectors when classes are narrowly separated. The effectiveness of the decomposition strategy is demonstrated using artificial spectra and applied to a ToF-SIMS materials science case study on the photodegradation of N719 dye, a common dye in photovoltaics, on a mesoporous TiO2 anode. The study revealed that the photodegradation process varies over time, and the resulting fragments have been identified accordingly. The proposed methodology, applicable to both labeled (supervised) and unlabeled (unsupervised) spectral data, can be seamlessly integrated into most modern mass spectrometry data analysis workflows to automatically generate a list of peaks whose relative behavior varies between two processes, and is particularly effective in identifying subtle differences between highly similar physicochemical processes.

Efficient microplastic identification by hyperspectral imaging: A comparative study of spatial resolutions, spectral ranges and classification models to define an optimal analytical protocol

Microplastics (MPs) pollution is a global and challenging issue, necessitating the development of efficient analytical strategies for their detection to monitor their environmental impact.This study aims to define an optimal analytical protocol for characterizing MPs by hyperspectral imaging (HSI), comparing different setups based on spatial resolution, spectral range and classification models. The investigated MPs include polymers commonly found in the environment, such as polystyrene (PS), polypropylene (PP) and high-density polyethylene (HDPE), subdivided in three size classes (1000–2000 μm, 500–1000 μm, 250–500 μm). Furthermore, MP particles with diameters ranging from 30 to 250 μm were assessed to determine the limit of detection (LOD) in the different configurations. Hyperspectral images were acquired with two spatial resolutions, 150 and 30 μm/pixel, and two spectral ranges, 1000–1700 nm (NIR) and 1000–2500 nm (SWIR). Three classification models, Partial Least Square-Discriminant Analysis (PLS-DA), Error Correction Output Coding-Support Vector Machine (ECOC-SVM) and Neural Network Pattern Recognition (NNPR) were tested on the acquired images. The correctness of these models was evaluated by prediction maps and statistical parameters (Recall, Specificity and Accuracy). The results demonstrated that for MP particles larger than 250 μm, the optimal setup is a spatial resolution of 150 μm/pixel and a spectral range of 1000–1700 nm, utilizing a linear classification model like PLS-DA. This approach offers accurate predictions while being time- and cost-efficient. For MPs smaller than 250 μm, a higher spatial resolution of 30 μm/pixel with a spectral range of 1000–2500 nm and a non-linear classification method like ECOC-SVM is preferable. The LOD is 250 μm for the 150 μm/pixel resolution and ranges from 100 to 200 μm for the 30 μm/pixel resolution. These findings provide a valuable guide for selecting the appropriate HSI acquisition conditions and data processing methods to optimally characterize MPs of different sizes.

B-274 Determining Novel Biomarker Candidates Associated With Heroin and Cocaine Exposure Using Urine Metabolomics

Abstract Background Substance abuse poses an escalating health risk in the United States. While acute drug exposure can be tracked using drugs and their metabolites as biomarkers in clinical settings, there is a notable absence of biomarkers for chronic drug exposure or addiction. The development and availability of such biomarkers could significantly enhance clinicians’ ability to identify patients at high risk of addiction, and more accurately predict disease progression and treatment responses. Methods Our study aimed to discover novel biomarkers associated with substance abuse by analyzing raw mass spectrometry (MS) data from urine comprehensive drug screening (UCDS) conducted at the University of Pittsburgh Medical Center (UPMC). The MS data, acquired through untargeted data collection using LC-qToF-MS at the UPMC Clinical Toxicology Laboratory, was initially preprocessed (including peak identification, alignment, and putative annotation) using MS-DIAL to generate a data matrix. This matrix, consisting of objects (cases) and features (m/z and retention time), was further normalized and analyzed using MetaboAnalyst. A combination of statistical methods, including point biserial correlation analysis, volcano plot, significance analysis of microarrays and metabolites (SAM), empirical Bayesian analysis of microarrays and metabolites (EBAM), partial least squares discriminant analysis (PLS-DA), and random forest (RF), were employed to select features significantly associated with the EIA-results. These features were subsequently evaluated for analyte identification using MS-FINDER. Results Our analysis identified nine significant features associated with 6MAM-EIA for heroin abuse, including 6-monoacetylmorphine itself and norfentanyl. For features associated with cocaine metabolite-EIA, 37 significant features were selected, including multiple cocaine metabolites, nicotine metabolites, and norfentanyl. Some of these selected features are likely products of in-source fragmentation or endogenous metabolites. Conclusions Our study has identified a set of potential biomarker candidates for illicit drug exposure. Notably, norfentanyl was found to be significantly associated with both 6MAM-EIA and cocaine metabolite-EIA, reflecting current trends in illicit drug use. Further chemical identification of these biomarkers is planned for future work.

Development and validation of a new method by MIR-FTIR and chemometrics for the early diagnosis of leprosy and evaluation of the treatment effect

ObjectiveDevelop a new method for diagnosing leprosy and monitoring the pharmacological treatment effect of patients. Material and methodsPlasma samples from patients diagnosed with leprosy (n = 211) who had not yet received any pharmacological treatment were collected at a basic health unit in Brazil. After treatment, samples were collected from the same patients (n = 125). Plasma samples from healthy volunteers were also collected (n = 179) and used as a control group. All samples were analyzed by Fourier transform mid-infrared spectrophotometry (MIR-FTIR). The spectral data of the samples were subjected to chemometric analysis. Principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA) were used to predict diagnosis and monitor pharmacological treatment. ResultsThe PCA model successfully distinguished among three sample classes: healthy individuals, pre-treatment leprosy patients, and post-treatment leprosy patients. The PLS-DA algorithm accurately classified healthy, treated, and diseased samples, facilitating both reliable diagnosis and treatment monitoring for leprosy. The model achieved a sensitivity of 97% to 100%, specificity of 100%, and accuracy ranging from 99% to 100%. Furthermore, when tested on plasma samples from patients with other conditions—renal failure (n=1032), hypertriglyceridemia (n=100), hypercholesterolemia (n=100), and mixed dyslipidemia (n=100)—the model correctly classified these as negative for leprosy, with diagnostic specificity between 93% and 96%. ConclusionThe MIR-FTIR technique combined with PLS-DA analysis proved to be a highly effective tool for screening leprosy patients and monitoring treatment outcomes. Given its low cost, this method could be easily implemented in laboratories across emerging and low-income countries.

Towards a Spectral Library of Medicinal and Aromatic Plant species (MAPs): Plant Discrimination and Wavelength Selection

The recognition and identification of Medicinal and Aromatic Plants species (MAPs) is a challenge for researchers and professionals in the field. To address this issue, this study aimed to examine the potential of using hyperspectral remote sensing, chemometrics and Machine Learning in discriminating between MAP species. Specifically, we tested the applicability of UV-Near-infrared Spectroscopy (UV-NIR), PCA and Partial Least-Squares Discriminant Analysis (PLS-DA) as tools for discrimination. The spectral signature data were obtained by UV-near infrared spectroscopy, covering a range of 325–1075 nm. Principal component analysis (PCA) was applied to reduce data dimensionality in order to minimize errors in PLS-DA model. This model was used to build a discriminant model based on the wavelengths obtained from PCA. The results show that it is effective to combine UV-NIR spectral features and PLS-DA to establish a discriminant model for accurately classifying the MAP species. The key wavelengths most involved in the discrimination were found in the NIR region and especially in ranges 516–548 and 628–1070 nm.

Non-Destructive Identification of Virgin Cashmere and Chemically Modified Wool Fibers Based on Fractional Order Derivative and Improved Wavelength Extraction Algorithm Using NIR Spectroscopy and Chemometrics

ABSTRACT Virgin cashmere is highly prized for its superior quality, and chemically modified wool is often used to fake it. However, traditional spectral analysis and image processing methods struggle to identify the two fibers. To address this, combining chemometrics with near-infrared (NIR) spectroscopy is proposed to identify virgin cashmere and chemically modified wool based on fractional order derivatives and improved wavelength extraction algorithm. The original spectra of the two fibers are very close, making identification difficult. Therefore, fractional order derivatives are used to amplify tiny spectral differences, which are often overlooked in conventional analysis. Meanwhile, common wavelength extraction algorithms few consider inherent relationship between spectral features and chemical properties, so an improved wavelength extraction algorithm using Shuffled Frog Leaping Algorithm (SFLA) and Beluga Whale Optimization (BWO) is employed to explore the connection of the two. The proposed method with Partial Least Squares Discriminant Analysis (PLS-DA) achieves an accuracy of 94.4%. Experimental results demonstrate that fractional order derivatives enhance tiny spectral features and differences, while extracted feature wavelengths correspond to main chemical characteristic bands of the fibers. This study shows the feasibility of identifying virgin cashmere and chemically modified wool and offers a novel idea for identifying fibers in the textile industry.

Investigating the detection of peanuts in chopped nut products using hyperspectral imaging systems

The intentional presence or cross-contamination of peanuts in other nut products can result in severe health problems for consumers allergic to peanuts. It is therefore essential to identify the presence of these allergenic compounds in commercialized nut products prior to their sale. For this purpose, we assessed the performance of a visible near infrared (Vis-NIR) and a shortwave infrared (SWIR) hyperspectral imaging (HSI) systems working in the spectral regions 419-1007 nm and 842-2532 nm, respectively, to identify peanut pieces in different chopped nuts (almonds, hazelnuts and walnuts). Two strategies were evaluated to create the training and validation sets. In Strategy I, these sets were composed of spectra belonging to individual pixels, whereas in Strategy II, the mean spectrum of each individual piece of nut was used. We used partial least squares discriminant analysis (PLS-DA) to develop the classification models, and the results were assessed by means of the values obtained for the sensitivity, specificity, and non-error rate (NER) statistics. The external validation procedure showed excellent classification results, with a NER of 98.3 % and 99.8 % for the Vis-NIR and SWIR systems, respectively, for Strategy I, and 100 % for both systems when Strategy II was followed. These results therefore confirm the viability of using HSI technology together with multivariate classification methods to detect peanut pieces in other chopped-nut products.

Use of NIR in COVID-19 Screening: Proof of Principles for Future Application.

The COVID-19 pandemic that affected the world between 2019 and 2022 showed the need for new tools to be tested and developed to be applied in global emergencies. Although standard diagnostic tools exist, such as the reverse-transcription polymerase chain reaction (RT-PCR), these tools have shown severe limitations when mass application is required. Consequently, a pressing need remains to develop a rapid and efficient screening test to deliver reliable results. In this context, near-infrared spectroscopy (NIRS) is a fast and noninvasive vibrational technique capable of identifying the chemical composition of biofluids. This study aimed to develop a rapid NIRS testing methodology to identify individuals with COVID-19 through the spectral analysis of swabs collected from the oral cavity. Swab samples from 67 hospitalized individuals were analyzed using NIR equipment. The spectra were preprocessed, outliers were removed, and classification models were constructed using partial least-squares for discriminant analysis (PLS-DA). Two models were developed: one with all the original variables and another with a limited number of variables selected using ordered predictors selection (OPS-DA). The OPS-DA model effectively reduced the number of redundant variables, thereby improving the diagnostic metrics. The model achieved a sensitivity of 92%, a specificity of 100%, an accuracy of 95%, and an AUROC of 94% for positive samples. These preliminary results suggest that NIRS could be a potential tool for future clinical application. A fast methodology for COVID-19 detection would facilitate medical diagnoses and laboratory routines, helping to ensure appropriate treatment.

A new approach to assess post-mortem interval: A machine learning-assisted label-free ATR-FTIR analysis of human vitreous humor

A crucial issue in forensics is determining the post-mortem interval (PMI), the time between death and the finding of a body. Despite various methods already employed for its estimation, only approximate values are currently achievable. Vitreous humor (VH) is an avascular tissue between the lens and the retina, mainly composed by a collagen fibers network, hyaluronic acid, and hyalocytes. Recently, it has received interest in forensic medicine, being easy to collect and susceptible to low microbiological contamination and putrefaction. Based on this evidence and thanks to the ability of Attenuated Total Reflectance – Fourier Transform InfraRed (ATR–FTIR) spectroscopy to perform fast analyses on a minimal sample amount, in this study, a new analytical approach to reliably estimate PMI is proposed combining ATR-FTIR analysis of VH human samples with multivariate statistical procedures, such as Principal Component Analysis (PCA) and Partial Least Squares-Discriminant Analysis (PLS-DA), for discriminant classification. Regression procedures, including Partial Least Squares Regression (PLSR), were performed: extremely positive results were obtained, and the most discriminant spectral features were highlighted (peaks at 1665, 1630, 1585, 1400, 1220, 1200, 1120, 854, 835, and 740 cm−1) and associated to PMI classes (average accuracy over 80 %). Specific and reliable markers able to correlate the macromolecular composition of VH with the PMI were identified, revealing a post-mortem protein degradation and amino acids deamination (decrease of proteins and increase of free amino acids and NH3), an increase of lactate, which diffuses from the retina to the VH, and changes in the hyaluronic acid component.

Classification of Mass Spectral Data to Assist in the Identification of Novel Synthetic Cannabinoids.

Detection and characterization of newly synthesized cannabinoids (NSCs) is challenging due to the lack of availability of reference standards and chemical data. In this study, a binary classification system was developed and validated using partial least square discriminant analysis (PLS-DA) by utilizing readily available mass spectral data of known drugs to assist in the identification of previously unknown NCSs. First, a binary classification model was developed to discriminate cannabinoids and cannabinoid-related compounds from other drug classes. Then, a classification model was developed to discriminate classical (THC-related) from synthetic cannabinoids. Additional models were developed based on the most abundant functional groups including core groups such as indole, indazole, azaindole, and naphthoylpyrrole, as well as head and tail groups including 4-fluorobenzyl (FUB) and 5-Fluoropentyl (5-F). The predictive ability of these models was tested via both cross-validation and external validation. The results show that all models developed are highly accurate. Additionally, latent variables (LVs) of each model provide useful mass to charge (m/z) for discrimination between classes, which further facilitates the identification of different functional groups of previously unknown drug molecules.

Explainable extreme gradient boosting as a machine learning tool for discrimination of the geographical origin of chili peppers using laser ablation-inductively coupled plasma mass spectrometry, X-ray fluorescence, and near-infrared spectroscopy

The spectroscopic discrimination of chili pepper samples according to geographical origin was executed using analytical techniques coupled with machine learning. First, laser ablation-inductively coupled plasma mass spectrometry (LA-ICP-MS), X-ray fluorescence (XRF), and near-infrared (NIR) spectroscopy were chosen for simple and rapid sample measurements. Second, to secure discrimination accuracy, eXtreme Gradient Boosting (XGBoost), a tree-based ensemble technique, was adopted as a potential classifier. Also, for explainable machine learning modeling, SHaply Additive exPlanation (SHAP) values of employed variables were calculated to assess how they contribute to the discrimination. The use of XGBoost improved discrimination accuracies in all three measurements compared to k-nearest neighbor (k-NN), support vector machine (SVM), and partial least squares-discriminant analysis (PLS-DA). The accuracy was 96.2 % using the LA-ICP-MS data. When the XRF and NIR data were combined, the accuracy improved to 97.5 %. The accuracy improvement was attributed to the combination of complementary atomic and molecular spectroscopic signatures of the samples.

Nondestructive diagnosis of mineral deficiencies in wheat leaves by one- or two-shot saturation pulse measurement of chlorophyll fluorescence and P700+ absorbance with machine learning

We hydroponically cultivated wheat and subjected them to mineral deficiency by a week-long exposure to Hoagland's solution minus one essential mineral. Chlorophyll fluorescence and P700+ absorbance were measured under a single 300 ms saturating light pulse (one-shot) or the conventional two pulses (two-shot). A machine learning-based multiclass classification model was developed to assess mineral deficiency diagnosis. The results indicated that partial least squares discriminant analysis (PLS-DA) was ineffective. Conversely, linear discriminant analysis (LDA) without principal components analysis (PCA) successfully identified 13 or 11 (with a class combining the control with Mo- and B-deficiencies; and ten other distinct classes for respective mineral deficiencies) classes of mineral deficiencies, achieving over 81 % diagnostic performance across all five macro metrics of precision, recall, specificity, accuracy, and F1 measure. The one-shot method exhibited only a slight decrease in performance compared to the two-shot method, highlighting the advantage of substantially reduced measurement time. Applying the developed LDA models to outdoor soil-grown leaf data revealed their practicality and limitations. In multiple deficiency scenarios, the model predicted one predominant deficiency or incorrectly diagnosed a different deficiency. This study is the first to quantitatively demonstrate the efficacy of ultra-fast nutritional diagnostic technology in identifying root zone mineral deficiencies using chlorophyll fluorescence and P700+ absorbance measurements. It delineates the requirements for constructing multilabel or quantitative calibration models for field deployment.